INDEX

Explanations

oscillation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åģ¶

-0.25

HEEL

-0.25

zig

-0.25

æĬĺèħ¾

-0.25

åĮ¡

-0.24

 scratch

-0.24

enny

-0.24

 sund

-0.23

inha

-0.23

kh

-0.23

POSITIVE LOGITS

ä¿Ŀä¿®

0.28

wolf

0.28

à¸²à¸ĩ

0.26

imension

0.26

è¢«æĬĵ

0.26

 brag

0.26

Nag

0.26

alus

0.25

aly

0.25

ä¹Łè¢«

0.25

Activations Density 0.004%

oscillation

No Comments

No Known Activations